Semi-supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning
Chenxia Wu, Jianke Zhu, Deng Cai, Chun Chen
Before downloading the material, please read and agree to the terms of using our datasets
and/or implementation. "Semi-supervised Nonlinear Hashing Using Bootstrap Sequential Projection Learning," Updated on 2012/06/09. Acknowledgments: Jun Wang's boosting-SPLH implementation, Fast-kmeans, etc. Requirement: Matlab, test in Matlab R2012a on Mac OS, but it might work in many other environments. Step 1: Download source code of our proposed BT-SPLH and BT-NSPLH methods. Step 2: Download MNIST data and extract the zip files into the 'data' folder. Step 3: Run 'demo.m'. The results of our proposed BT-SPLH and BT-NSPLH in Fig.5(a) and Fig.6(a) will be reproduced. Bug reports are welcome. Please contact Chenxia Wu (chenxiawu at cs.cornell dot edu).
Manuscript
Chenxia Wu, Jianke Zhu, Deng Cai and Chun Chen
IEEE Trans. on Knowledge Data Engineering, accepted. (PDF Code Data)
Brief Guide
Back to Chenxia Wu's Homepage